Pinecone

Fully managed vector database with high performance at scale. Supports metadata filtering, namespaces, and hybrid search. Best for production workloads.

Syntax

vector-databases

index.upsert(vectors=[...])
index.query(vector=..., top_k=10, filter={...})

Example

vector-databases

from pinecone import Pinecone

pc = Pinecone(api_key="...")
index = pc.Index("my-index")

# Upsert vectors:
index.upsert(vectors=[
    ("id1", [0.1, 0.2, ...], {"category": "tech"}),
    ("id2", [0.3, 0.4, ...], {"category": "science"}),
])

# Query with metadata filter:
results = index.query(
    vector=query_vec,
    top_k=5,
    filter={"category": {"$eq": "tech"}}
)